3 items with this tag.
Professional curricula are comprehensively documented but not systematically queryable, creating artificial information scarcity. This creates significant problems for institutions: regulatory compliance reporting consumes weeks of staff time, quality assurance requires exhaustive manual verification, and curriculum office teams cannot efficiently answer structural questions. Current approaches—manual document review, VLE keyword search, curriculum mapping spreadsheets, and purpose-built curriculum management systems—fail to expose curriculum structure in queryable form. We propose an architecture where graph databases become the source of truth for curriculum structure, with vector databases for content retrieval and the Model Context Protocol providing accessible interfaces. This makes documented curriculum structure explicitly queryable—prerequisite chains, competency mappings, and assessment coverage—enabling compliance verification in hours rather than weeks. The architecture suits AI-forward institutions—those treating AI integration as ongoing strategic practice requiring active engagement with evolving technologies. Technology handles structural verification; educators retain essential authority over educational meaning-making. The proposal argues for removing technical barriers to interrogating curriculum complexity rather than eliminating that complexity through technological solution.
The current discourse around artificial intelligence in education has become preoccupied with prompting strategies, overlooking more fundamental questions about the nature of context in human-AI collaboration. This paper explores the concept of *context engineering* as an operational framework that supports personal learning and the philosophical goal of *context sovereignty*. Drawing from complexity science and learning theory, we argue that context functions as a dynamic field of meaning-making rather than static background information, and that ownership of that context is an essential consideration. Current approaches to context-setting in AI-supported learning—primarily prompting and document uploading—create episodic burdens requiring learners to adapt to AI systems rather than insisting that AI systems adapt to learners. Context sovereignty offers an alternative paradigm based on three principles: persistent understanding, individual agency, and cognitive extension. This framework addresses concerns about privacy, intellectual challenge, and authentic assessment while enabling new forms of collaborative learning that preserve human agency. Rather than treating AI as an external tool requiring skilful manipulation, context sovereignty suggests AI can become a cognitive partner that understands and extends human thinking while respecting individual boundaries. The implications extend beyond technical implementation to fundamental questions about the nature of learning, assessment, and human-AI collaboration in educational settings.